custom_manage

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full disclosure burden and does well: it reveals session-only scoping, that params are 'forwarded unvalidated' to the addon handler, batch incompatibility for deferred tools, and the flat-parameter compatibility alias. It stops short of covering error behavior for an unknown tool_name, a minor gap given the dynamic nature of the tools.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded and every paragraph earns its place (op semantics, batch interaction, alternative routing, call-shape alias). It is dense but not padded; the only minor inefficiency is repeating 'custom' terminology across closely-packed paragraphs that could be slightly tightened.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex, dynamic tool with no annotations and zero schema coverage, the description covers purpose, both operations, parameter shape, batching constraints, alternative first-class registration, and call format. An output schema exists, so return-value omission is excused. It falls just short of perfect only by not describing failure modes for invalid tool names or session handling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate — and it does thoroughly. It explains the meaning of each op enum value, specifies that op='invoke' requires a tool_name string plus an optional params dict whose shape follows the params_schema returned by op='list', and even provides the canonical JSON call shape. This adds far more meaning than the bare schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The first line, 'List or invoke custom tools registered by third-party addons,' pairs specific verbs (list/invoke) with a specific resource (custom tools from third-party addons), unambiguously distinguishing it from the many sibling *_manage tools. The purpose is concrete and immediately usable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit routing guidance: state when to use it, and name the alternative — 'Some custom tools are also registered first-class as custom_<name> with their own schema — prefer those when present.' It also sets preconditions ('Active session only') and constraints for the sibling batch_execute (deferred tools cannot run in batches).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.